!pip install display

Requirement already satisfied: display in c:\users\redmi\appdata\roaming\python\python312\site-packages (1.0.0)

# --- Import & Apply CSS File ---
from IPython.display import display, HTML

def apply_css():
    return HTML('<style>' + open('style.css', 'r').read() + '</style>')
apply_css()

# Library dasar untuk manipulasi dan analisis data
import pandas as pd
import numpy as np

# Library untuk visualisasi
import matplotlib.pyplot as plt
import seaborn as sns
from matplotlib import style
import matplotlib.ticker as ticker

# Library untuk pemodelan dan evaluasi
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LinearRegression
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_error
from sklearn.model_selection import cross_val_score, GridSearchCV

# Konfigurasi visualisasi
style.use('seaborn-v0_8-whitegrid')
plt.rcParams['figure.figsize'] = (12, 8)
plt.rcParams['font.family'] = 'DejaVu Sans'
sns.set_palette('Blues_r')
# Menekan warning
import warnings
warnings.filterwarnings('ignore')

# Untuk menampilkan semua kolom
pd.set_option('display.max_columns', None)

# Membaca dataset
diamonds = pd.read_csv('diamonds.csv')

# Melihat 5 baris pertama
print("5 baris pertama dari dataset:")
diamonds.head()

5 baris pertama dari dataset:

# Informasi dasar dataset
print("Informasi Dataset:")
diamonds.info()

# Statistik deskriptif
print("\nStatistik Deskriptif:")
diamonds.describe()

Informasi Dataset:
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 53940 entries, 0 to 53939
Data columns (total 11 columns):
 #   Column      Non-Null Count  Dtype  
---  ------      --------------  -----  
 0   Unnamed: 0  53940 non-null  int64  
 1   carat       53940 non-null  float64
 2   cut         53940 non-null  object 
 3   color       53940 non-null  object 
 4   clarity     53940 non-null  object 
 5   depth       53940 non-null  float64
 6   table       53940 non-null  float64
 7   price       53940 non-null  int64  
 8   x           53940 non-null  float64
 9   y           53940 non-null  float64
 10  z           53940 non-null  float64
dtypes: float64(6), int64(2), object(3)
memory usage: 4.5+ MB

Statistik Deskriptif:

# Memeriksa jumlah nilai unik pada variabel kategorikal
print("Jumlah nilai unik pada variabel kategorikal:")
print(f"cut: {diamonds['cut'].nunique()} nilai unik")
print(f"color: {diamonds['color'].nunique()} nilai unik")
print(f"clarity: {diamonds['clarity'].nunique()} nilai unik")

# Menampilkan nilai unik
print("\nNilai unik untuk setiap variabel kategorikal:")
print(f"cut: {diamonds['cut'].unique()}")
print(f"color: {diamonds['color'].unique()}")
print(f"clarity: {diamonds['clarity'].unique()}")

Jumlah nilai unik pada variabel kategorikal:
cut: 5 nilai unik
color: 7 nilai unik
clarity: 8 nilai unik

Nilai unik untuk setiap variabel kategorikal:
cut: ['Ideal' 'Premium' 'Good' 'Very Good' 'Fair']
color: ['E' 'I' 'J' 'H' 'F' 'G' 'D']
clarity: ['SI2' 'SI1' 'VS1' 'VS2' 'VVS2' 'VVS1' 'I1' 'IF']

# Memilih hanya variabel numerik (kecuali indeks)
numeric_cols = ['carat', 'depth', 'table', 'price', 'x', 'y', 'z']

# Membuat histograms untuk semua variabel numerik
fig, axes = plt.subplots(nrows=3, ncols=3, figsize=(20, 18))
axes = axes.flatten()

for i, col in enumerate(numeric_cols):
    sns.histplot(data=diamonds, x=col, kde=True, ax=axes[i], color='#3D5A80')
    axes[i].set_title(f'Distribusi {col}', fontsize=14, fontweight='bold')
    axes[i].set_xlabel(col, fontsize=12)
    axes[i].set_ylabel('Frekuensi', fontsize=12)

# Menambahkan subplot kosong jika perlu
for j in range(i+1, len(axes)):
    axes[j].set_visible(False)

plt.tight_layout()
plt.show()

# Menampilkan statistik untuk memahami skewness dan outliers
diamonds[numeric_cols].describe().T

# Variabel kategorikal
cat_cols = ['cut', 'color', 'clarity']

# Membuat countplots
fig, axes = plt.subplots(nrows=1, ncols=3, figsize=(20, 6))

for i, col in enumerate(cat_cols):
    counts = diamonds[col].value_counts().sort_index()
    sns.barplot(x=counts.index, y=counts.values, ax=axes[i], palette='Blues')
    axes[i].set_title(f'Distribusi {col}', fontsize=14, fontweight='bold')
    axes[i].set_xlabel(col, fontsize=12)
    axes[i].set_ylabel('Jumlah', fontsize=12)

    # Menambahkan label pada setiap bar
    for p in axes[i].patches:
        axes[i].annotate(f'{int(p.get_height())}',
                         (p.get_x() + p.get_width() / 2., p.get_height()),
                         ha='center', va='center', xytext=(0, 10),
                         textcoords='offset points')

plt.tight_layout()
plt.show()

# Scatterplots antara variabel numerik dan harga
numeric_predictors = ['carat', 'depth', 'table', 'x', 'y', 'z']

fig, axes = plt.subplots(nrows=2, ncols=3, figsize=(20, 12))
axes = axes.flatten()

for i, col in enumerate(numeric_predictors):
    sns.scatterplot(data=diamonds, x=col, y='price', alpha=0.3, ax=axes[i], color='#3D5A80')
    axes[i].set_title(f'Hubungan {col} vs Price', fontsize=14, fontweight='bold')
    axes[i].set_xlabel(col, fontsize=12)
    axes[i].set_ylabel('Price ($)', fontsize=12)

plt.tight_layout()
plt.show()

# Menghitung korelasi
correlation = diamonds[numeric_cols].corr()
print("Korelasi dengan harga:")
print(correlation['price'].sort_values(ascending=False))

# Heatmap korelasi
plt.figure(figsize=(12, 10))
sns.heatmap(correlation, annot=True, cmap='Blues', fmt='.2f', linewidths=0.5)
plt.title('Matriks Korelasi Variabel Numerik', fontsize=16, fontweight='bold')
plt.show()

Korelasi dengan harga:
price    1.000000
carat    0.921591
x        0.884435
y        0.865421
z        0.861249
table    0.127134
depth   -0.010647
Name: price, dtype: float64

# Boxplots untuk melihat distribusi harga berdasarkan variabel kategorikal
fig, axes = plt.subplots(nrows=1, ncols=3, figsize=(20, 6))

for i, col in enumerate(cat_cols):
    order = None
    if col == 'cut':
        order = ['Fair', 'Good', 'Very Good', 'Premium', 'Ideal']
    elif col == 'color':
        order = ['J', 'I', 'H', 'G', 'F', 'E', 'D']
    elif col == 'clarity':
        order = ['I1', 'SI2', 'SI1', 'VS2', 'VS1', 'VVS2', 'VVS1', 'IF']

    sns.boxplot(data=diamonds, x=col, y='price', ax=axes[i], order=order, palette='Blues')
    axes[i].set_title(f'Distribusi Price berdasarkan {col}', fontsize=14, fontweight='bold')
    axes[i].set_xlabel(col, fontsize=12)
    axes[i].set_ylabel('Price ($)', fontsize=12)

    # Rotasi label sumbu x jika diperlukan
    if len(diamonds[col].unique()) > 5:
        axes[i].set_xticklabels(axes[i].get_xticklabels(), rotation=45)

plt.tight_layout()
plt.show()

# Agregasi statistik harga berdasarkan variabel kategorikal
for col in cat_cols:
    print(f"\nStatistik harga berdasarkan {col}:")
    print(diamonds.groupby(col)['price'].agg(['mean', 'median', 'min', 'max', 'count']).sort_values('mean', ascending=False))

Statistik harga berdasarkan cut:
                  mean  median  min    max  count
cut                                              
Premium    4584.257704  3185.0  326  18823  13791
Fair       4358.757764  3282.0  337  18574   1610
Very Good  3981.759891  2648.0  336  18818  12082
Good       3928.864452  3050.5  327  18788   4906
Ideal      3457.541970  1810.0  326  18806  21551

Statistik harga berdasarkan color:
              mean  median  min    max  count
color                                        
J      5323.818020  4234.0  335  18710   2808
I      5091.874954  3730.0  334  18823   5422
H      4486.669196  3460.0  337  18803   8304
G      3999.135671  2242.0  354  18818  11292
F      3724.886397  2343.5  342  18791   9542
D      3169.954096  1838.0  357  18693   6775
E      3076.752475  1739.0  326  18731   9797

Statistik harga berdasarkan clarity:
                mean  median  min    max  count
clarity                                        
SI2      5063.028606  4072.0  326  18804   9194
SI1      3996.001148  2822.0  326  18818  13065
VS2      3924.989395  2054.0  334  18823  12258
I1       3924.168691  3344.0  345  18531    741
VS1      3839.455391  2005.0  327  18795   8171
VVS2     3283.737071  1311.0  336  18768   5066
IF       2864.839106  1080.0  369  18806   1790
VVS1     2523.114637  1093.0  336  18777   3655

# Scatterplot dengan multiple variabel
plt.figure(figsize=(12, 10))
sns.scatterplot(data=diamonds, x='carat', y='price', hue='cut', size='depth',
                sizes=(20, 200), alpha=0.5, palette='viridis')
plt.title('Hubungan antara Carat, Price, Cut, dan Depth', fontsize=16, fontweight='bold')
plt.xlabel('Carat', fontsize=14)
plt.ylabel('Price ($)', fontsize=14)
plt.legend(title='Cut', fontsize=12, title_fontsize=14)
plt.show()

# Pairplot untuk melihat hubungan antar variabel numerik dan kategorikal
plt.figure(figsize=(12, 10))
sns.pairplot(diamonds.sample(5000), hue='cut', vars=['carat', 'depth', 'table', 'price', 'x'],
             palette='viridis', diag_kind='kde', height=2.5)
plt.suptitle('Pairplot Variabel Numerik berdasarkan Cut', fontsize=16, y=1.02)
plt.show()

# Hubungan carat dan price berdasarkan clarity
g = sns.FacetGrid(diamonds, col="clarity", col_wrap=4, height=4, aspect=1.2)
g.map_dataframe(sns.scatterplot, x="carat", y="price", alpha=0.5, color='#3D5A80')
g.set_axis_labels("Carat", "Price ($)")
g.set_titles(col_template="{col_name}")
g.fig.suptitle('Hubungan Carat dan Price berdasarkan Clarity', fontsize=16, y=1.02)
plt.tight_layout()
plt.show()

<Figure size 1200x1000 with 0 Axes>

# Melihat kolom pertama yang tampaknya hanya indeks
diamonds.columns

Index(['Unnamed: 0', 'carat', 'cut', 'color', 'clarity', 'depth', 'table',
       'price', 'x', 'y', 'z'],
      dtype='object')

# Menghapus kolom indeks
diamonds = diamonds.drop(diamonds.columns[0], axis=1)

# Memeriksa kolom setelah penghapusan
diamonds.columns

Index(['carat', 'cut', 'color', 'clarity', 'depth', 'table', 'price', 'x', 'y',
       'z'],
      dtype='object')

# Mencari outlier pada variabel numerik
def plot_boxplot(df, columns, figsize=(20, 10)):
    fig, axes = plt.subplots(nrows=1, ncols=len(columns), figsize=figsize)

    if len(columns) == 1:
        axes = [axes]

    for i, col in enumerate(columns):
        sns.boxplot(y=df[col], ax=axes[i], color='#3D5A80')
        axes[i].set_title(f'Boxplot {col}', fontsize=14, fontweight='bold')
        axes[i].set_ylabel(col, fontsize=12)

    plt.tight_layout()
    plt.show()

# Boxplot untuk variabel numerik
plot_boxplot(diamonds, ['carat', 'depth', 'table', 'price', 'x', 'y', 'z'])

# Mendeteksi outlier menggunakan IQR
def detect_outliers(df, column):
    Q1 = df[column].quantile(0.25)
    Q3 = df[column].quantile(0.75)
    IQR = Q3 - Q1

    lower_bound = Q1 - 1.5 * IQR
    upper_bound = Q3 + 1.5 * IQR

    outliers = df[(df[column] < lower_bound) | (df[column] > upper_bound)]

    return outliers, lower_bound, upper_bound

# Memeriksa jumlah outlier untuk setiap variabel numerik
for col in ['carat', 'depth', 'table', 'price', 'x', 'y', 'z']:
    outliers, lower, upper = detect_outliers(diamonds, col)
    print(f"Outlier pada {col}: {len(outliers)} baris ({len(outliers)/len(diamonds)*100:.2f}%)")
    print(f"Batas bawah: {lower:.2f}, Batas atas: {upper:.2f}")
    print(f"Min: {diamonds[col].min():.2f}, Max: {diamonds[col].max():.2f}")
    print("---")

Outlier pada carat: 1889 baris (3.50%)
Batas bawah: -0.56, Batas atas: 2.00
Min: 0.20, Max: 5.01
---
Outlier pada depth: 2545 baris (4.72%)
Batas bawah: 58.75, Batas atas: 64.75
Min: 43.00, Max: 79.00
---
Outlier pada table: 605 baris (1.12%)
Batas bawah: 51.50, Batas atas: 63.50
Min: 43.00, Max: 95.00
---
Outlier pada price: 3540 baris (6.56%)
Batas bawah: -5611.38, Batas atas: 11885.62
Min: 326.00, Max: 18823.00
---
Outlier pada x: 32 baris (0.06%)
Batas bawah: 1.96, Batas atas: 9.29
Min: 0.00, Max: 10.74
---
Outlier pada y: 29 baris (0.05%)
Batas bawah: 1.99, Batas atas: 9.27
Min: 0.00, Max: 58.90
---
Outlier pada z: 49 baris (0.09%)
Batas bawah: 1.22, Batas atas: 5.73
Min: 0.00, Max: 31.80
---

# Memeriksa apakah ada nilai 0 atau negatif pada dimensi berlian
zero_dimensions = diamonds[(diamonds['x'] <= 0) | (diamonds['y'] <= 0) | (diamonds['z'] <= 0)]
print(f"Jumlah berlian dengan dimensi 0 atau negatif: {len(zero_dimensions)}")
if len(zero_dimensions) > 0:
    print(zero_dimensions)

Jumlah berlian dengan dimensi 0 atau negatif: 20
       carat        cut color clarity  depth  table  price     x     y    z
2207    1.00    Premium     G     SI2   59.1   59.0   3142  6.55  6.48  0.0
2314    1.01    Premium     H      I1   58.1   59.0   3167  6.66  6.60  0.0
4791    1.10    Premium     G     SI2   63.0   59.0   3696  6.50  6.47  0.0
5471    1.01    Premium     F     SI2   59.2   58.0   3837  6.50  6.47  0.0
10167   1.50       Good     G      I1   64.0   61.0   4731  7.15  7.04  0.0
11182   1.07      Ideal     F     SI2   61.6   56.0   4954  0.00  6.62  0.0
11963   1.00  Very Good     H     VS2   63.3   53.0   5139  0.00  0.00  0.0
13601   1.15      Ideal     G     VS2   59.2   56.0   5564  6.88  6.83  0.0
15951   1.14       Fair     G     VS1   57.5   67.0   6381  0.00  0.00  0.0
24394   2.18    Premium     H     SI2   59.4   61.0  12631  8.49  8.45  0.0
24520   1.56      Ideal     G     VS2   62.2   54.0  12800  0.00  0.00  0.0
26123   2.25    Premium     I     SI1   61.3   58.0  15397  8.52  8.42  0.0
26243   1.20    Premium     D    VVS1   62.1   59.0  15686  0.00  0.00  0.0
27112   2.20    Premium     H     SI1   61.2   59.0  17265  8.42  8.37  0.0
27429   2.25    Premium     H     SI2   62.8   59.0  18034  0.00  0.00  0.0
27503   2.02    Premium     H     VS2   62.7   53.0  18207  8.02  7.95  0.0
27739   2.80       Good     G     SI2   63.8   58.0  18788  8.90  8.85  0.0
49556   0.71       Good     F     SI2   64.1   60.0   2130  0.00  0.00  0.0
49557   0.71       Good     F     SI2   64.1   60.0   2130  0.00  0.00  0.0
51506   1.12    Premium     G      I1   60.4   59.0   2383  6.71  6.67  0.0

# Menghapus baris dengan dimensi 0 atau negatif
diamonds_cleaned = diamonds[(diamonds['x'] > 0) & (diamonds['y'] > 0) & (diamonds['z'] > 0)]
print(f"Jumlah baris sebelum pembersihan: {len(diamonds)}")
print(f"Jumlah baris setelah pembersihan: {len(diamonds_cleaned)}")
print(f"Jumlah baris yang dihapus: {len(diamonds) - len(diamonds_cleaned)}")

# Menetapkan dataset bersih untuk analisis selanjutnya
diamonds = diamonds_cleaned

Jumlah baris sebelum pembersihan: 53940
Jumlah baris setelah pembersihan: 53920
Jumlah baris yang dihapus: 20

# Memeriksa ordinalitas variabel kategorikal
for col in cat_cols:
    print(f"Variabel: {col}")
    if col == 'cut':
        order = ['Fair', 'Good', 'Very Good', 'Premium', 'Ideal']
    elif col == 'color':
        order = ['J', 'I', 'H', 'G', 'F', 'E', 'D']
    elif col == 'clarity':
        order = ['I1', 'SI2', 'SI1', 'VS2', 'VS1', 'VVS2', 'VVS1', 'IF']

    temp_df = diamonds.groupby(col)['price'].mean().reset_index()
    temp_df = temp_df.sort_values('price', ascending=False)

    print("Urutan berdasarkan harga rata-rata:")
    print(temp_df)

    print(f"Urutan teoritis: {order}")
    print("---")

Variabel: cut
Urutan berdasarkan harga rata-rata:
         cut        price
3    Premium  4579.684543
0       Fair  4357.500932
4  Very Good  3981.664101
1       Good  3926.403509
2      Ideal  3456.941201
Urutan teoritis: ['Fair', 'Good', 'Very Good', 'Premium', 'Ideal']
---
Variabel: color
Urutan berdasarkan harga rata-rata:
  color        price
6     J  5323.818020
5     I  5089.973990
4     H  4480.942155
3     G  3996.876551
2     F  3725.080205
0     D  3168.106436
1     E  3076.752475
Urutan teoritis: ['J', 'I', 'H', 'G', 'F', 'E', 'D']
---
Variabel: clarity
Urutan berdasarkan harga rata-rata:
  clarity        price
3     SI2  5060.440174
2     SI1  3994.112608
0      I1  3926.189702
5     VS2  3922.866819
4     VS1  3839.144308
7    VVS2  3283.737071
1      IF  2864.839106
6    VVS1  2519.512315
Urutan teoritis: ['I1', 'SI2', 'SI1', 'VS2', 'VS1', 'VVS2', 'VVS1', 'IF']
---

# Membagi fitur dan target
X = diamonds.drop('price', axis=1)
y = diamonds['price']

# Membagi data menjadi training dan testing set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

print(f"Jumlah data training: {len(X_train)}")
print(f"Jumlah data testing: {len(X_test)}")

# Membuat pipeline preprocessing
# Identifikasi kolom numerik dan kategorikal
numeric_features = ['carat', 'depth', 'table', 'x', 'y', 'z']
categorical_features = ['cut', 'color', 'clarity']

# Membuat preprocessor
preprocessor = ColumnTransformer(
    transformers=[
        ('num', StandardScaler(), numeric_features),
        ('cat', OneHotEncoder(drop='first'), categorical_features)
    ])

# Memeriksa hasil preprocessing
preprocessing_pipeline = Pipeline(steps=[('preprocessor', preprocessor)])
X_train_processed = preprocessing_pipeline.fit_transform(X_train)

print(f"Bentuk data sebelum preprocessing: {X_train.shape}")
print(f"Bentuk data setelah preprocessing: {X_train_processed.shape}")

Jumlah data training: 43136
Jumlah data testing: 10784
Bentuk data sebelum preprocessing: (43136, 9)
Bentuk data setelah preprocessing: (43136, 23)

# Pipeline untuk Linear Regression
lr_pipeline = Pipeline(steps=[
    ('preprocessor', preprocessor),
    ('regressor', LinearRegression())
])

# Training model
lr_pipeline.fit(X_train, y_train)

# Prediksi pada data testing
y_pred_lr = lr_pipeline.predict(X_test)

# Evaluasi model
mse_lr = mean_squared_error(y_test, y_pred_lr)
rmse_lr = np.sqrt(mse_lr)
r2_lr = r2_score(y_test, y_pred_lr)
mae_lr = mean_absolute_error(y_test, y_pred_lr)

print("Multiple Linear Regression:")
print(f"Mean Squared Error (MSE): {mse_lr:.2f}")
print(f"Root Mean Squared Error (RMSE): {rmse_lr:.2f}")
print(f"R-squared (R²): {r2_lr:.4f}")
print(f"Mean Absolute Error (MAE): {mae_lr:.2f}")

# Visualisasi hasil prediksi
plt.figure(figsize=(10, 8))
plt.scatter(y_test, y_pred_lr, alpha=0.5, color='#3D5A80')
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'r--')
plt.xlabel('Harga Aktual ($)', fontsize=12)
plt.ylabel('Harga Prediksi ($)', fontsize=12)
plt.title('Perbandingan Harga Aktual vs Prediksi (Linear Regression)', fontsize=16, fontweight='bold')
plt.grid(True, alpha=0.3)
plt.show()

# Residual plot
residuals_lr = y_test - y_pred_lr
plt.figure(figsize=(10, 8))
plt.scatter(y_pred_lr, residuals_lr, alpha=0.5, color='#3D5A80')
plt.axhline(y=0, color='r', linestyle='--')
plt.xlabel('Harga Prediksi ($)', fontsize=12)
plt.ylabel('Residual', fontsize=12)
plt.title('Residual Plot (Linear Regression)', fontsize=16, fontweight='bold')
plt.grid(True, alpha=0.3)
plt.show()

Multiple Linear Regression:
Mean Squared Error (MSE): 1290368.13
Root Mean Squared Error (RMSE): 1135.94
R-squared (R²): 0.9195
Mean Absolute Error (MAE): 726.30

# Pipeline untuk Random Forest Regression
rf_pipeline = Pipeline(steps=[
    ('preprocessor', preprocessor),
    ('regressor', RandomForestRegressor(n_estimators=100, random_state=42))
])

# Training model
rf_pipeline.fit(X_train, y_train)

# Prediksi pada data testing
y_pred_rf = rf_pipeline.predict(X_test)

# Evaluasi model
mse_rf = mean_squared_error(y_test, y_pred_rf)
rmse_rf = np.sqrt(mse_rf)
r2_rf = r2_score(y_test, y_pred_rf)
mae_rf = mean_absolute_error(y_test, y_pred_rf)

print("Random Forest Regression:")
print(f"Mean Squared Error (MSE): {mse_rf:.2f}")
print(f"Root Mean Squared Error (RMSE): {rmse_rf:.2f}")
print(f"R-squared (R²): {r2_rf:.4f}")
print(f"Mean Absolute Error (MAE): {mae_rf:.2f}")

# Visualisasi hasil prediksi
plt.figure(figsize=(10, 8))
plt.scatter(y_test, y_pred_rf, alpha=0.5, color='#3D5A80')
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'r--')
plt.xlabel('Harga Aktual ($)', fontsize=12)
plt.ylabel('Harga Prediksi ($)', fontsize=12)
plt.title('Perbandingan Harga Aktual vs Prediksi (Random Forest)', fontsize=16, fontweight='bold')
plt.grid(True, alpha=0.3)
plt.show()

# Residual plot
residuals_rf = y_test - y_pred_rf
plt.figure(figsize=(10, 8))
plt.scatter(y_pred_rf, residuals_rf, alpha=0.5, color='#3D5A80')
plt.axhline(y=0, color='r', linestyle='--')
plt.xlabel('Harga Prediksi ($)', fontsize=12)
plt.ylabel('Residual', fontsize=12)
plt.title('Residual Plot (Random Forest)', fontsize=16, fontweight='bold')
plt.grid(True, alpha=0.3)
plt.show()

# Feature importance
rf_model = rf_pipeline.named_steps['regressor']
preprocessor = rf_pipeline.named_steps['preprocessor']

# Mendapatkan nama fitur setelah preprocessing
ohe = preprocessor.named_transformers_['cat']
cat_features_encoded = ohe.get_feature_names_out(categorical_features)
feature_names = np.concatenate([numeric_features, cat_features_encoded])

# Mendapatkan feature importance
importances = rf_model.feature_importances_

# Mengurutkan feature importance
indices = np.argsort(importances)[::-1]

# Visualisasi feature importance
plt.figure(figsize=(12, 8))
plt.title('Feature Importance (Random Forest)', fontsize=16, fontweight='bold')
plt.bar(range(len(indices)), importances[indices], color='#3D5A80')
plt.xticks(range(len(indices)), feature_names[indices], rotation=90)
plt.xlabel('Fitur', fontsize=12)
plt.ylabel('Importance', fontsize=12)
plt.tight_layout()
plt.show()

Random Forest Regression:
Mean Squared Error (MSE): 346873.45
Root Mean Squared Error (RMSE): 588.96
R-squared (R²): 0.9784
Mean Absolute Error (MAE): 286.91

# Membuat DataFrame untuk perbandingan metrik
metrics = {
    'Model': ['Multiple Linear Regression', 'Random Forest Regression'],
    'MSE': [mse_lr, mse_rf],
    'RMSE': [rmse_lr, rmse_rf],
    'MAE': [mae_lr, mae_rf],
    'R-squared': [r2_lr, r2_rf],
    'Mean CV R-squared': [cv_scores_lr.mean(), cv_scores_rf.mean()],
    'Std CV R-squared': [cv_scores_lr.std(), cv_scores_rf.std()]
}

metrics_df = pd.DataFrame(metrics)
metrics_df

# Visualisasi perbandingan metrik
fig, axes = plt.subplots(nrows=1, ncols=3, figsize=(18, 12))
axes = axes.flatten()

# RMSE
sns.barplot(x='Model', y='RMSE', data=metrics_df, ax=axes[0], palette=['#3D5A80', '#2A9D8F'])
axes[0].set_title('Perbandingan RMSE', fontsize=14, fontweight='bold')
axes[0].set_ylabel('RMSE ($)', fontsize=12)
axes[0].bar_label(axes[0].containers[0], fmt='%.2f')

# MAE
sns.barplot(x='Model', y='MAE', data=metrics_df, ax=axes[1], palette=['#3D5A80', '#2A9D8F'])
axes[1].set_title('Perbandingan MAE', fontsize=14, fontweight='bold')
axes[1].set_ylabel('MAE ($)', fontsize=12)
axes[1].bar_label(axes[1].containers[0], fmt='%.2f')

# R-squared
sns.barplot(x='Model', y='R-squared', data=metrics_df, ax=axes[2], palette=['#3D5A80', '#2A9D8F'])
axes[2].set_title('Perbandingan R-squared', fontsize=14, fontweight='bold')
axes[2].set_ylabel('R-squared', fontsize=12)
axes[2].bar_label(axes[2].containers[0], fmt='%.4f')

plt.tight_layout()
plt.show()

# Perbandingan langsung prediksi kedua model
plt.figure(figsize=(12, 10))
plt.scatter(y_test, y_pred_lr, alpha=0.5, color='#3D5A80', label='Linear Regression')
plt.scatter(y_test, y_pred_rf, alpha=0.5, color='#2A9D8F', label='Random Forest')
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'r--')
plt.xlabel('Harga Aktual ($)', fontsize=12)
plt.ylabel('Harga Prediksi ($)', fontsize=12)
plt.title('Perbandingan Prediksi Linear Regression vs Random Forest', fontsize=16, fontweight='bold')
plt.legend()
plt.grid(True, alpha=0.3)
plt.show()

# Perbandingan distribusi error
plt.figure(figsize=(12, 8))
sns.histplot(residuals_lr, kde=True, color='#3D5A80', alpha=0.5, label='Linear Regression')
sns.histplot(residuals_rf, kde=True, color='#2A9D8F', alpha=0.5, label='Random Forest')
plt.axvline(x=0, color='r', linestyle='--')
plt.xlabel('Residual ($', fontsize=12)
plt.ylabel('Frekuensi', fontsize=12)
plt.title('Distribusi Residual', fontsize=16, fontweight='bold')
plt.legend()
plt.grid(True, alpha=0.3)
plt.show()

Variabel	Deskripsi	Tipe Data
carat	Berat berlian (0.2 - 5.01)	Numerik (Float)
cut	Kualitas potongan berlian (Fair, Good, Very Good, Premium, Ideal)	Kategorikal
color	Warna berlian, dari J (terburuk) hingga D (terbaik)	Kategorikal
clarity	Kejernihan berlian (I1, SI2, SI1, VS2, VS1, VVS2, VVS1, IF)	Kategorikal
depth	Persentase kedalaman total = z / mean(x, y) = 2 * z / (x + y) (43--79)	Numerik (Float)
table	Lebar bagian atas berlian relatif terhadap titik terlebar (43--95)	Numerik (Float)
price	Harga berlian dalam dollar AS (\$326 - \$18,823)	Numerik (Integer)
x	Panjang dalam mm (0 - 10.74)	Numerik (Float)
y	Lebar dalam mm (0 - 58.9)	Numerik (Float)
z	Kedalaman dalam mm (0 - 31.8)	Numerik (Float)

	Unnamed: 0	carat	depth	table	price	x	y	z
count	53940.000000	53940.000000	53940.000000	53940.000000	53940.000000	53940.000000	53940.000000	53940.000000
mean	26970.500000	0.797940	61.749405	57.457184	3932.799722	5.731157	5.734526	3.538734
std	15571.281097	0.474011	1.432621	2.234491	3989.439738	1.121761	1.142135	0.705699
min	1.000000	0.200000	43.000000	43.000000	326.000000	0.000000	0.000000	0.000000
25%	13485.750000	0.400000	61.000000	56.000000	950.000000	4.710000	4.720000	2.910000
50%	26970.500000	0.700000	61.800000	57.000000	2401.000000	5.700000	5.710000	3.530000
75%	40455.250000	1.040000	62.500000	59.000000	5324.250000	6.540000	6.540000	4.040000
max	53940.000000	5.010000	79.000000	95.000000	18823.000000	10.740000	58.900000	31.800000

	count	mean	std	min	25%	50%	75%	max
carat	53940.0	0.797940	0.474011	0.2	0.40	0.70	1.04	5.01
depth	53940.0	61.749405	1.432621	43.0	61.00	61.80	62.50	79.00
table	53940.0	57.457184	2.234491	43.0	56.00	57.00	59.00	95.00
price	53940.0	3932.799722	3989.439738	326.0	950.00	2401.00	5324.25	18823.00
x	53940.0	5.731157	1.121761	0.0	4.71	5.70	6.54	10.74
y	53940.0	5.734526	1.142135	0.0	4.72	5.71	6.54	58.90
z	53940.0	3.538734	0.705699	0.0	2.91	3.53	4.04	31.80

Hubungan antara Variabel Numerik dan Harga
¶

8. | Evaluasi dan Perbandingan Model 📊
¶

Perbandingan Metrik Evaluasi
¶

9. | Analisis Hasil dan Kesimpulan 🔎
¶

9.1 Analisis Performa Model
¶

9.2 Analisis Feature Importance
¶

9.3 Kesimpulan dan Rekomendasi
¶

10. | Referensi dan Sumber Data 📚
¶

	Unnamed: 0	carat	cut	color	clarity	depth	table	price	x	y	z
0	1	0.23	Ideal	E	SI2	61.5	55.0	326	3.95	3.98	2.43
1	2	0.21	Premium	E	SI1	59.8	61.0	326	3.89	3.84	2.31
2	3	0.23	Good	E	VS1	56.9	65.0	327	4.05	4.07	2.31
3	4	0.29	Premium	I	VS2	62.4	58.0	334	4.20	4.23	2.63
4	5	0.31	Good	J	SI2	63.3	58.0	335	4.34	4.35	2.75

Hubungan antara Variabel Numerik dan Harga¶

8. | Evaluasi dan Perbandingan Model 📊¶

Perbandingan Metrik Evaluasi¶

9. | Analisis Hasil dan Kesimpulan 🔎¶

9.1 Analisis Performa Model¶

9.2 Analisis Feature Importance¶

9.3 Kesimpulan dan Rekomendasi¶

10. | Referensi dan Sumber Data 📚¶

Hubungan antara Variabel Numerik dan Harga
¶

8. | Evaluasi dan Perbandingan Model 📊
¶

Perbandingan Metrik Evaluasi
¶

9. | Analisis Hasil dan Kesimpulan 🔎
¶

9.1 Analisis Performa Model
¶

9.2 Analisis Feature Importance
¶

9.3 Kesimpulan dan Rekomendasi
¶

10. | Referensi dan Sumber Data 📚
¶